Algorithmic fairness in language models

Grainne McKnight

Founding Data Scientist,

Gráinne is a Data Scientist based in Berlin. Her first job was with a more traditional German bank in Dublin where she worked on credit modelling for over two years. In 2018 she moved to Berlin to work as a Data Scientist with N26. There she built several data products, including a customer service chatbot, a geolocation service and models for money laundering and fraud detection. In 2020 she moved to Amsterdam where she worked on fraud detection models at Adyen and also led a small team of data analysts and scientists. In October of 2021, Graáinne moved back to Berlin (she missed Berlin!) and she is now working on exciting new things at Spoke - a start-up that hopes to use AI to help teams communicate effortlessly.

Grainne McKnight
Grainne McKnight
Session description

Measuring bias is an important step for understanding and addressing unfairness in NLP and ML models. This can be achieved using fairness metrics which quantify the differences in a model's behaviour across a range of demographic groups. In this workshop, we will introduce you to these metrics in addition to general practices to promote algorithmic fairness.

By the end of the workshop, you will:

  • Understand why it is important to detect and mitigate algorithmic bias in language models

  • Understand how algorithmic bias can materialize in language models

  • Be able to measure and mitigate bias in pre-trained word embeddings



  • Presentation on why we need fairness and bias mitigation tools with examples

  • Breakout discussions on real-life cases and causes of bias

Bias Measurement:

  • Calculating the bias of a pre-trained word embedding in python within a Deepnote notebook

  • Visualizing and comparing bias across word embeddings in python

Bias Mitigation:

  • De-biasing word embeddings in python



  • We will use Deepnote to work together on python notebooks in the workshop. Access is possible by signing up for free with a google or github account, this can be done either in advance or on the day of the workshop.

  • Basic knowledge of python is required and experience working with word embeddings is an advantage